Drilldown: Recipe

DeepSeek V4.1 Flash heretic on 4x 8 GB · DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) · DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build) · DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) · DeepSeek V4.1 Flash on 4x 8 GB (GNmac) · DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) · DeepSeek V4.1 Flash on 4x 8 GB plus RTX PRO 6000 (ExLlamaV3 TP5) · DeepSeek V4.1 Flash on 6x 8 GB (Deepinfer-SM80 TP2 x PP3) · DeepSeek V4.1 Flash on 6x 8 GB (TP6) · DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) · DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 layer split) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 TP2) · GLM 5.3 Flash on 2x 8 GB (Project Maya) · GLM 5.3 Flash on 3x 8 GB · GLM 5.3 Flash on 4x 8 GB · GLM 5.3 on 8x 8 GB (Int4-Int8Mix PP8) · GLM 5.3 on 8x 8 GB (vllm-170hx-glm5) · MiMo V2.6 Flash on 4x 8 GB · Qwen3.8 27B on 1x 8 GB (W4A16 vLLM) · Qwen3.8 Flash Next on 1x 8 GB (ElectroHobo 3 bpw) · Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE) · Qwen3.8 Flash Next on 2x 8 GB (DUFRelic PP2) · Qwen3.8 Flash Next on 2x 8 GB (ElectroHobo W4A16 TP2) · Qwen3.8 Flash Next on 2x 8 GB (mannydelrio PP2) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) · Qwen3.8 Flash Next on 2x 8 GB (Plean PP2) · Qwen3.8 Flash Next on 2x 8 GB (vektorprime PP2) · Qwen3.8 Flash Next on 3x 8 GB (clee PP3) · Qwen3.8 Flash Next on 4x 8 GB · Other · None

DeepSeek-V4.1-Flash-1017 (1) · Qwen3.8-Flash-Next (1) · Qwen3.8-Flash-Next-Uncensored (refusal-removed, from orcarouter) (1)

AWQ W4A16 g32 (leoncca/Qwen3.8-Flash-Next-Uncensored-AWQ-g32); PLE table converted to INT4 and served from SSD (1) · Mixed INT4 AutoRound (Minachist/Qwen3.8-Flash-Next-INT4-Mixed-AutoRound, about 65 GB) with the full BF16 PLE table on NVMe (1) · Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1)

vLLM 0.29.1rc1 nightly plus the checkpoint author's patches (1) · vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 (1) · wtdcode/vllm-backport 3142ded1 plus a two-file patch and two tinybeast PLE plugins (venv, no container) (1)

None (1) · recipe 31318fd; patches 0001-0020 (1) · vllm-backport 3142ded1 (1)

8 GB (3)

2 (2) · 8 (1)

PP2 (layer partition 25,23), no P2P (1) · PP2, MTP 3, no P2P (1) · PP8, partition 5,5,5,5,5,5,5,5 (1)

1,048,576 (1) · 262,144 (1) · 262,144 (256K in the post) (1)

117 (1) · 177.8 (1) · 197 (1)

5,800 (1) · 6,066 (1) · 7,006 (1)

64 GB (1) · 64 GB, --gpu-memory-utilization 0.94, TB_TORCH_MEM_CAP_GIB=61.5 (1) · 64 GB; weights 35.9 GB per rank (ranks 1-6), 37.6 GB rank 0, 46.3 GB rank 7 (1)

None (1) · 180 W (1) · 180 W (one card unstable at 250 W) (1)

None (2) · nvidia-open 610.43.02 + cmpunlocker v0.5 or newer (1)

None (1) · cmpunlocker v0.5+ (sudo ./install.sh --profile=8gb --no-iommu) (1) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) (1)

Reported (3)

mrmannyatx (1) · plean. (1) · Zanooda (1)

October 7, 2026 (1) · October 15, 2026 (1) · October 19, 2026 (1)

https://github.com/mannydelrio/qwen38-flash-next-2x-cmp170hx (1) · https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1) · https://www.bozocentral.com/2x-cmp170hx-qwen3-flash-next (1)